Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Modelling cognitive development with constructivist neural networks
AU - Westermann, G
PY - 2000
Y1 - 2000
N2 - Based on recent evidence from cognitive developmental neuroscience, I argue for the importance of constructivist models of cognitive developmental phenomena. This point is empirically investigated with a constructivist neural network model of the acquisition of past tense/participle inflections. The model dynamically adapts its architecture to the learning task by growing units and connections in a task-specific way during learning. In contrast to other, fixed-architecture models, the constructivist network displays a realistic, U-shaped learning behaviour. In the trained network, realistic "adult" representations emerge that lead to aphasia-like dissociations between regular and irregular forms when the model is lesioned. These results show that constructivist neural networks form valid models of cognitive developmental processes and that they avoid many of the problems of fixed-architecture models.
AB - Based on recent evidence from cognitive developmental neuroscience, I argue for the importance of constructivist models of cognitive developmental phenomena. This point is empirically investigated with a constructivist neural network model of the acquisition of past tense/participle inflections. The model dynamically adapts its architecture to the learning task by growing units and connections in a task-specific way during learning. In contrast to other, fixed-architecture models, the constructivist network displays a realistic, U-shaped learning behaviour. In the trained network, realistic "adult" representations emerge that lead to aphasia-like dissociations between regular and irregular forms when the model is lesioned. These results show that constructivist neural networks form valid models of cognitive developmental processes and that they avoid many of the problems of fixed-architecture models.
KW - GERMAN INFLECTION
KW - LANGUAGE
KW - MORPHOLOGY
KW - CORTEX
KW - RULES
M3 - Conference contribution/Paper
SN - 1-85233-354-5
SP - 123
EP - 132
BT - Connectionist models of learning, development and evolution
A2 - French, Robert M.
A2 - Sougne, Jacques P.
PB - Springer Verlag London Ltd
CY - Godalming
T2 - 6th Neural Computation and Psychology Workshop
Y2 - 16 September 2000 through 18 September 2000
ER -